| .. |
|
sub_modules
|
99d4c97afc
支持batch-ocr-det，速度约提升3倍（200页pdf在3090上）
|
hai 6 meses |
|
__init__.py
|
489f70e91d
refactor(magic_pdf): move model config variables
|
hai 11 meses |
|
batch_analyze.py
|
7c1d7dff65
fix(batch): disable OCR detection batch processing by default
|
hai 5 meses |
|
doc_analyze_by_custom_model.py
|
93ad41edce
feat(ocr): add PPHGNetV2_B4 backbone and update OCR models
|
hai 6 meses |
|
magic_model.py
|
fb02be19c9
fix: caption match
|
hai 9 meses |
|
model_list.py
|
735f3a7059
feat(model): add language detection model and update related modules
|
hai 10 meses |
|
pdf_extract_kit.py
|
d7d85a2881
feat(ocr): implement language-specific OCR processing
|
hai 8 meses |
|
pp_structure_v2.py
|
9b4d77dcd4
fix(lite_model): Adapt iite Mode to the Hybrid OCR Mode in Version 0.10
|
hai 1 ano |
myhloli
7c1d7dff65
fix(batch): disable OCR detection batch processing by default